A Concise and Provably Informative Multi‐Scale Signature Based on Heat Diffusion

Sun, Jian; Ovsjanikov, Maks; Guibas, Leonidas J.

doi:10.1111/j.1467-8659.2009.01515.x

Cited by 1,236 publications

(1,155 citation statements)

References 23 publications

Supporting

Mentioning

1,146

Contrasting

Unclassified

Order By: Relevance

“…One of them is to design powerful 3D shape signatures that can capture the intrinsic geometric information of the CAD models, with the motivation that the query and the database samples are essentially the same type of 3D models. To this end, various local features have been developed to describe the local geometry of 3D models, including MeshHoG as a 3D extension of the SIFT feature [7], Heat Kernel Signature [8] [11], and Intrinsic Shape Context [9]. Realizing the sensitivity to model noise for those local descriptors [15], researchers also proposed to use high-level topological features [19][20], or aggregate low-level features to mid-level representations such as the extended Bag-of-Words model [10][21] and graph correspondences [22].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

Wang

Feng

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. The recent advances of low-cost and mobile depth sensors dramatically extend the potential of 3D shape retrieval and analysis. While the traditional research of 3D retrieval mainly focused on searching by a rough 2D sketch or with a high-quality CAD model, we tackle a novel and challenging problem of cross-domain 3D shape retrieval, in which users can use 3D scans from low-cost depth sensors like Kinect as queries to search CAD models in the database. To cope with the imperfection of user-captured models such as model noise and occlusion, we propose a cross-domain shape retrieval framework, which minimizes the potential function of a Conditional Random Field to efficiently generate the retrieval scores. In particular, the potential function consists of two critical components: one unary potential term provides robust crossdomain partial matching and the other pairwise potential term embeds spatial structures to alleviate the instability from model noise. Both potential components are efficiently estimated using random forests with 3D local features, forming a Regression Tree Field framework. We conduct extensive experiments on two recently released user-captured 3D shape datasets and compare with several state-of-the-art approaches on the cross-domain shape retrieval task. The experimental results demonstrate that our proposed method outperforms the competing methods with a significant performance gain.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Although great progress has been made in 3D feature design, such as spin-image based descriptor [6], MeshDOG/MeshHOG [7], Heat Kernel Signature (HKS) [8] [11], and Intrinsic Shape Context (ISC) descriptor [9], these low-level shape features highly rely on the quality of the 3D models and ...…”

Section: Introductionmentioning

confidence: 99%

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

Wang

Feng

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

show abstract

“…These method are simple and robust, but less ability to distinguish, and can't be used for precise matching. The more ability of description methods are Fourier method, wavelet description method, measuring distance [1], shape context [2] [3], integral invariants [4], Heat Kernel [5].…”

Section: A Component-stroke Detectionmentioning

confidence: 99%

Component-stroke Corresponding System for Chinese Characters of Different Styles

Che¹,

Liang²,

Yue³

2015

Proceedings of the 2015 International Conference on Computer Science and Intelligent Communication

View full text Add to dashboard Cite

Abstract-Stroke and shape of the Chinese character with different script has changed hugely among different style. To present the correspondence between Chinese characters component-strokes, this paper designs a component-stroke corresponding system for Chinese characters based on sematic knowledge. Firstly, we acquire the correspondence between components by the way of semi-automatic. Then we get the feature points from the intersection of skeleton and contour by skeleton algorithm, finally we finish the Chinese character component-stroke correspondence process. Our system can present a robust and fast component-strokes correspondence results.

show abstract

“…Similarly, other features can also be considered within such potentials, such as multiscale heat kernel signatures [35] and eigenfunctions of the Laplace-Beltrami operator [33].…”

Section: Non-rigid 3d Surface Matchingmentioning

confidence: 99%

Modeling Shapes with Higher-Order Graphs: Methodology and Applications

Wang

Zeng

Samaras

et al. 2013

Shape Perception in Human and Computer Vision

View full text Add to dashboard Cite

Extrinsic factors such as object pose and camera parameters are a main source of shape variability and pose an obstacle to efficiently solving shape matching and inference. Most existing methods address the influence of extrinsic factors by decomposing the transformation of the source shape (model) into two parts: one corresponding to the extrinsic factors and the other accounting for intra-class variability and noise, which are solved in a successive or alternating manner. In this chapter, we consider a methodology to circumvent the influence of extrinsic factors by exploiting shape properties that are invariant to them. Based on higher-order graph-based models, we implement such a methodology to address various important vision problems, such as non-rigid 3D surface matching and knowledge-based 3D segmentation, in a one-shot optimization scheme. Experimental results demonstrate the superior performance and potential of this type of approach.

show abstract

A Concise and Provably Informative Multi‐Scale Signature Based on Heat Diffusion

Abstract: We propose a novel point signature based on the properties of the heat diffusion process on a shape. Our

Cited by 1,236 publications

References 23 publications

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields

Component-stroke Corresponding System for Chinese Characters of Different Styles

Modeling Shapes with Higher-Order Graphs: Methodology and Applications

Contact Info

Product

Resources

About